Related papers: Towards Less Constrained Macro-Neural Architecture…
Neural Architecture Search (NAS) has been explosively studied to automate the discovery of top-performer neural networks. Current works require heavy training of supernet or intensive architecture evaluations, thus suffering from heavy…
Designing state encoders for reinforcement learning (RL) with multiple information sources -- such as sensor measurements, time-series signals, image observations, and textual instructions -- remains underexplored and often requires manual…
The recent progress of deep convolutional neural networks has enabled great success in single image super-resolution (SISR) and many other vision tasks. Their performances are also being increased by deepening the networks and developing…
Applying machine learning to sensitive time-series data is often bottlenecked by the iteration loop: Performance depends strongly on preprocessing and architecture, yet training often has to run on-premise under strict data-local…
Neural Architecture Search (NAS) automates and prospers the design of neural networks. Estimator-based NAS has been proposed recently to model the relationship between architectures and their performance to enable scalable and flexible…
Neural architecture search (NAS) has become an important approach to automatically find effective architectures. To cover all possible good architectures, we need to search in an extremely large search space with billions of candidate…
Neural Architecture Search (NAS) has shown promising capability in learning text representation. However, existing text-based NAS neither performs a learnable fusion of neural operations to optimize the architecture, nor encodes the latent…
Neural Architectures Search (NAS) becomes more and more popular over these years. However, NAS-generated models tends to suffer greater vulnerability to various malicious attacks. Lots of robust NAS methods leverage adversarial training to…
Artificial neural network (NN) architecture design is a nontrivial and time-consuming task that often requires a high level of human expertise. Neural architecture search (NAS) serves to automate the design of NN architectures and has…
The discovery of neural architectures from simple building blocks is a long-standing goal of Neural Architecture Search (NAS). Hierarchical search spaces are a promising step towards this goal but lack a unifying search space design…
3D convolution neural networks (CNN) have been proved very successful in parsing organs or tumours in 3D medical images, but it remains sophisticated and time-consuming to choose or design proper 3D networks given different task contexts.…
Spatial-temporal sequence forecasting (STSF) is a long-standing research problem with widespread real-world applications. Neural architecture search (NAS), which automates the neural network design, has been shown effective in tackling the…
Neural architecture search (NAS) algorithms save tremendous labor from human experts. Recent advancements further reduce the computational overhead to an affordable level. However, it is still cumbersome to deploy the NAS techniques in…
Recent advances in neural architecture search (NAS) demand tremendous computational resources, which makes it difficult to reproduce experiments and imposes a barrier-to-entry to researchers without access to large-scale computation. We aim…
In class-incremental learning, a model learns continuously from a sequential data stream in which new classes occur. Existing methods often rely on static architectures that are manually crafted. These methods can be prone to capacity…
The existing neural architecture search algorithms are mostly working on search spaces with short-distance connections. We argue that such designs, though safe and stable, obstacles the search algorithms from exploring more complicated…
The significant computational cost of multiplications hinders the deployment of deep neural networks (DNNs) on edge devices. While multiplication-free models offer enhanced hardware efficiency, they typically sacrifice accuracy. As a…
Performing analytical tasks over graph data has become increasingly interesting due to the ubiquity and large availability of relational information. However, unlike images or sentences, there is no notion of sequence in networks. Nodes…
In neural architecture search (NAS), the space of neural network architectures is automatically explored to maximize predictive accuracy for a given task. Despite the success of recent approaches, most existing methods cannot be directly…
Recently, neural architecture search (NAS) methods have attracted much attention and outperformed manually designed architectures on a few high-level vision tasks. In this paper, we propose HiNAS (Hierarchical NAS), an effort towards…